Ytsma, CR;
Dyar, MD;
Lepore, K;
Watts, JC;
King, JL;
(2025)
Empirical portable x-ray fluorescence quantification limits and accuracies for 28 elements within 1942 diverse geological standards using open-source machine learning.
Spectrochimica Acta Part B: Atomic Spectroscopy
, 231
, Article 107241. 10.1016/j.sab.2025.107241.
![[thumbnail of Ytsma_submission_manuscript_20250513.pdf]](https://discovery.ucl.ac.uk/style/images/fileicons/text.png) |
Text
Ytsma_submission_manuscript_20250513.pdf Access restricted to UCL open access staff until 20 June 2026. Download (2MB) |
Abstract
Portable X-Ray Fluorescence (pXRF) instruments are commonly used to quantify elements within materials due to their portability and quick results using a fundamental parameters approach and a data library. Results can also be customized by assembling alternative data libraries instead of the included calibrations that are typically provided with such systems. In contrast, this paper presents an alternate approach to the standard fundamental parameters (FP) protocol. We instead empirically quantify elemental abundances directly from pXRF spectra using multivariate (MVA) methods trained on 1942 geochemical standards. Prediction accuracies (RMSE-P) and limits of quantification (LOQ) are presented for six major (Al<inf>2</inf>O<inf>3</inf>, CaO, Fe<inf>2</inf>O<inf>3</inf>, MgO, SiO<inf>2</inf>, TiO<inf>2</inf>), two minor (MnO, P<inf>2</inf>O<inf>5</inf>), and 20 trace elements (As, Bi, Cr, Cu, Mo, Nb, Ni, Pb, Rb, SO<inf>3</inf>, Sn, Sr, Ta, Th, U, V, W, Y, Zn, Zr). Partial least squares (PLS) regression was chosen as the optimal MVA method from five other linear methods (ElasticNet, Ridge, OMP, PCR, LASSO). The resultant MVA models have accuracies comparable to instrument-based FP calibrations, and are more sensitive to low concentrations. This work demonstrates a powerful and adaptable open-source method for quantifying elements using XRF spectra that should be considered as a viable alternative to traditional FP approaches. The large and diverse geochemical dataset used here is made publicly available to encourage further study and combination of datasets with calibration transfer.
| Type: | Article |
|---|---|
| Title: | Empirical portable x-ray fluorescence quantification limits and accuracies for 28 elements within 1942 diverse geological standards using open-source machine learning |
| DOI: | 10.1016/j.sab.2025.107241 |
| Publisher version: | https://doi.org/10.1016/j.sab.2025.107241 |
| Language: | English |
| Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. |
| Keywords: | Science & Technology, Technology, Spectroscopy, Machine learning, XRF, Calibration, Prediction, Accuracy, Multivariate, Geochemistry, INDUCED BREAKDOWN SPECTROSCOPY, VARIABLE SELECTION, RAMAN-SPECTROSCOPY, CALIBRATION, SPECTROMETER, PREDICTION, PXRF, TRANSMISSION, UNIVARIATE |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Population Health Sciences > Institute of Health Informatics UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Population Health Sciences > Institute of Health Informatics > Clinical Epidemiology |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10213890 |
Archive Staff Only
 |
View Item |
